Deep Learning in the Wild
It addresses practical deployment issues for practitioners and researchers applying deep learning to new domains, though it is incremental in focusing on lessons learned rather than new methods.
This paper examines the practical challenges of applying deep learning to novel real-world tasks without existing baselines, based on case studies from industry collaborations in areas like face matching and quality control, and provides best practices to bridge the gap between algorithmic developments and implementation.
Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research \& development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty-gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.